In an illustrative embodiment, an automated system determines rental income and location quality for geographic regions using customized data sets. The system can generate customized location feature sets for applying to trained location quality prediction models where the feature sets include hybrid features combining aspects of two or more items of the location feature data into a single hybrid feature and the geographic regions are sized to a predetermined granularity level. Each feature set associated with a geographic region can be applied to a machine learning data model trained to predict rental property income at the respective predefined region from the customized location feature sets. Using the output data from the machine learning data model, the system can calculate location metrics quantifying a rental property income and the location quality for the geographic region.
Legal claims defining the scope of protection, as filed with the USPTO.
2. The system of claim 1, wherein each variable of at least one of the one or more hybrid variables combines geospatial feature data with one or more items of economic data or demographic data.
3. The system of claim 2, wherein the one or more hybrid variables comprises at least one of a distance to a metro station or a distance to a highway.
4. The system of claim 1, wherein the first geographic granularity level of the plurality of geographic granularity levels is a census tract level.
5. The system of claim 4, wherein further geographic granularity levels of the plurality of geographic granularity levels comprise a zip code granularity level, a county granularity level, and a metropolitan statistical area (MSA) granularity level.
6. The system of claim 1, wherein the one or more location metrics comprise a rental income prediction score, a metropolitan statistical area (MSA) ranking percentile, and a location quality score.
7. The system of claim 1, wherein the one or more location metrics comprise a feature-level score for each feature variable of the plurality of feature variables that impacts the rental property income at the respective predefined geographic region.
8. The system of claim 1, wherein the corresponding machine learning data model is an Extreme Gradient Boosting (XGBoost) data model.
9. The system of claim 1, wherein the plurality of data sources includes two or more of external geospatial data sources, external demographic data sources, or external economic data sources.
11. The method of claim 10, wherein each variable of at least one of the one or more hybrid variables combines geospatial feature data with one or more items of economic data or demographic data.
12. The method of claim 11, wherein the one or more hybrid variables comprise at least one of a distance to a metro station or a distance to a highway.
13. The method of claim 10, wherein the first geographic granularity level of the plurality of geographic granularity levels is a census tract level.
14. The method of claim 13, wherein further geographic granularity levels of the plurality of geographic granularity levels comprise a zip code granularity level, a county granularity level, and a metropolitan statistical area (MSA) granularity level.
15. The method of claim 10, wherein the one or more location metrics comprise a rental income prediction score, metropolitan statistical area (MSA) ranking percentile, and location quality score.
16. The method of claim 10, wherein the one or more location metrics comprise a feature-level score for each feature variable of the plurality of feature variables that impacts the rental property income at the respective predefined geographic region.
17. The system of claim 1, wherein the second geographic granularity level is smaller than the first geographic granularity level.
18. The system of claim 1, wherein aggregating comprises calculating a weighted average of the data values corresponding to each region of the two or more regions.
19. The system of claim 1, wherein transforming the data values to generate each respective location feature set of one or more of the plurality of second customized location feature sets comprises imputing, based on data values of one or more neighboring regions of the plurality of second predefined regions, data values for one or more variables of the plurality of feature variables.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
July 21, 2021
December 10, 2024
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.